Navigation Approach Research Articles

HEX: a safe research framework for hybrid EMT X-ray navigation

PurposeNavigating with continuous X-ray provides visual guidance, but exposes both surgeon and patient to ionizing radiation, which is associated with serious health risks. Interleaving fluoro snapshots with electromagnetic tracking (EMT) potentially minimizes radiation.MethodsWe propose hybrid EMT + X-ray (HEX), a research framework for navigation with an emphasis on safe experimentation. HEX is based on several hardware and software components that are orchestrated to allow for safe and efficient data acquisition.ResultsIn our study, hybrid navigation reduces radiation by 71% with cubic, and by 40% with linear error compensation while achieving submillimeter accuracy. Training points for compensation can be reduced by half while keeping a similar accuracy–radiation trade-off.ConclusionThe HEX framework allows to safely and efficiently evaluate the hybrid navigation approach in simulated procedures. Complementing intraoperative X-ray with EMT significantly reduces radiation in the OR, increasing the safety of patients and surgeons.

A bio-inspired robot navigation model based on the environmental cognitive mechanism of the rat brain hippocampus

Self-positioning and goal-oriented navigation behaviors in complex and variable environments are important capabilities that mammals rely on for survival in the natural world. To this end, this article proposes a robot navigation model with bio-inspired environmental cognition and autonomous localization capabilities based on the spatial cognitive mechanism of the hippocampus in the rat brain. The model constructs a cognitive map by integrating its own motion cues and visual observation features, and uses the dynamic predictive relationship between each location cognitive node to achieve a goal-oriented navigation process. The research approach in this article will provide inspirational implications for a robot navigation approach with brain-like cognitive mechanisms.

A self-guided approach for navigation in a minimalistic foraging robotic swarm

We present a biologically inspired design for swarm foraging based on ant’s pheromone deployment, where the swarm is assumed to have very restricted capabilities. The robots do not require global or relative position measurements and the swarm is fully decentralized and needs no infrastructure in place. Additionally, the system only requires one-hop communication over the robot network, we do not make any assumptions about the connectivity of the communication graph and the transmission of information and computation is scalable versus the number of agents. This is done by letting the agents in the swarm act as foragers or as guiding agents (beacons). We present experimental results computed for a swarm of Elisa-3 robots on a simulator, and show how the swarm self-organizes to solve a foraging problem over an unknown environment, converging to trajectories around the shortest path, and test the approach on a real swarm of Elisa-3 robots. At last, we discuss the limitations of such a system and propose how the foraging efficiency can be increased.

Quality-Aware Autonomous Navigation with Dynamic Path Cost for Vision-Based Mapping toward Drone Landing

This article presents a novel autonomous navigation approach that is capable of increasing map exploration and accuracy while minimizing the distance traveled for autonomous drone landings. For terrain mapping, a probabilistic sparse elevation map is proposed to represent measurement accuracy and enable the increasing of map quality by continuously applying new measurements with Bayes inference. For exploration, the Quality-Aware Best View (QABV) planner is proposed for autonomous navigation with a dual focus: map exploration and quality. Generated paths allow for visiting viewpoints that provide new measurements for exploring the proposed map and increasing its quality. To reduce the distance traveled, we handle the path-cost information in the framework of control theory to dynamically adjust the path cost of visiting a viewpoint. The proposed methods handle the QABV planner as a system to be controlled and regulate the information contribution of the generated paths. As a result, the path cost is increased to reduce the distance traveled or decreased to escape from a low-information area and avoid getting stuck. The usefulness of the proposed mapping and exploration approach is evaluated in detailed simulation studies including a real-world scenario for a packet delivery drone.

Cubature H∞ Filter based Simultaneous Localization and Mapping

For many real-real applications, autonomous navigation is necessary for many vehicles, including ground, underwater, and aerial vehicles. Simultaneous Localization and Mapping (SLAM) is an important approach for autonomous navigation in unknown environments and/or GPS-denied areas. In SLAM, by using the sensors embedded in the vehicle, the vehicle simultaneously builds a map and localise in that map. In this paper, a solution to the SLAM is proposed using cubature H∞filter (CH∞F). CH∞F is a derivative-free filter, which can deal with highly nonlinear and Gaussian or non-Gaussian systems. It has the desired features of both the cubature Kalman filter and H∞filter, deals with nonlinear and uncertain sensor dynamics. In this paper, CH∞F has been proposed for the SLAM application. Different simulation scenarios are considered and compared.

RDNN for Classification and Prediction of Rock or Mine in Underwater Acoustics

Mines in the waters are just explosives that detonate upon contact with an object. The underwater submarine must foresee if it will encounter a mine or a rock. Lacking the development of the Ranging Sound Navigation approach, which utilizes particular variables to identify whether a surface or a barrier is made of a mine or rock, finding mines or rocks would have been extremely difficult. In our study, we demonstrate a technique for predicting underwater rocks and mines using SONAR waves. At 60 different angles, SONAR pings are employed to record the various frequencies of submerged objects. To identify whether the object in the ocean is a mine or just a rock, the submarine uses SONAR signals, which transmit sound and receive switchbacks. The mine and rock categories are predicted using the prediction models. To create these prediction models, Supervised Machine Learning Classification methods were employed.

An autonomous navigation approach for unmanned vehicle in off-road environment with self-supervised traversal cost prediction

An autonomous navigation approach for unmanned vehicle in off-road environment with self-supervised traversal cost prediction

Performance-Based Navigation Approach Procedures with Barometric Vertical Guidance: How to Select the Air Temperature for Approach Procedure Design

In performance-based navigation (PBN) procedures with barometric vertical guidance, the effective vertical path angle (VPA) depends on the actual air temperature at the time of approach execution. A very low design temperature could result in an obstacle clearance height (OCH) higher than needed; hence, the airport throughput could be reduced when the cloud ceiling is below the OCH. Conversely, the design of a low temperature higher than is practical could lead to long periods in which the procedure cannot be used. The results of this research show that there is not much difference between the effective VPA for the different low temperatures studied. However, this slight difference, when obstacles penetrating the final approach surface (FAS) exist, usually leads to the approach minima being significantly different from each other. The objective of this study was to analyse the impact of the selected designed low temperatures in PBN procedures with barometric vertical guidance on the OCH/runway throughput and approach periods of use balance. Finally, guidelines on the selection of the minimum designed low temperature are proposed.

Reinforcement and Curriculum Learning for Off-Road Navigation of an UGV with a 3D LiDAR

This paper presents the use of deep Reinforcement Learning (RL) for autonomous navigation of an Unmanned Ground Vehicle (UGV) with an onboard three-dimensional (3D) Light Detection and Ranging (LiDAR) sensor in off-road environments. For training, both the robotic simulator Gazebo and the Curriculum Learning paradigm are applied. Furthermore, an Actor-Critic Neural Network (NN) scheme is chosen with a suitable state and a custom reward function. To employ the 3D LiDAR data as part of the input state of the NNs, a virtual two-dimensional (2D) traversability scanner is developed. The resulting Actor NN has been successfully tested in both real and simulated experiments and favorably compared with a previous reactive navigation approach on the same UGV.

Real-Time Navigation with Guide Template for Pedicle Screw Placement Using an Augmented Reality Head-Mounted Device: A Proof-of-Concept Study.

This study aims to explore the real-time navigation with guide template using an augmented reality head-mounted device (ARHMD) for pedicle screw placement. The spatial coordinate relationships between augmented reality images and real objects were established through the custom-made guide template, and the registration and tracking were completed using an ARHMD. The feasibility and accuracy of this method were verified by pedicle screw placement in 2 lumbar models. According to the Gertzbein-Robbins grading scale, the accuracy of pedicle screw placement was assessed. The navigation errors were estimated by measuring the deviation values of entry point and trajectory angle. A total of 20 pedicle K-wires were placed into L1-L5 in 2 lumbar models, which were successfully completed, with an average time of 11.5min per model and 69s per screw. The overall K-wires placement accuracy was 100% (20 screws). The navigation error was 2.77 ± 0.82mm for the deviation value of entry point, and 3.03° ± 0.94° for the deviation value of trajectory angle. The application of an ARHMD combined with guide template for pedicle screw placement is a promising navigation approach.

Swarm Cooperative Navigation Using Centralized Training and Decentralized Execution

The demand for autonomous UAV swarm operations has been on the rise following the success of UAVs in various challenging tasks. Yet conventional swarm control approaches are inadequate for coping with swarm scalability, computational requirements, and real-time performance. In this paper, we demonstrate the capability of emerging multi-agent reinforcement learning (MARL) approaches to successfully and efficiently make sequential decisions during UAV swarm collaborative tasks. We propose a scalable, real-time, MARL approach for UAV collaborative navigation where members of the swarm have to arrive at target locations at the same time. Centralized training and decentralized execution (CTDE) are used to achieve this, where a combination of negative and positive reinforcement is employed in the reward function. Curriculum learning is used to facilitate the sought performance, especially due to the high complexity of the problem which requires extensive exploration. A UAV model that highly resembles the respective physical platform is used for training the proposed framework to make training and testing realistic. The scalability of the platform to various swarm sizes, speeds, goal positions, environment dimensions, and UAV masses has been showcased in (1) a load drop-off scenario, and (2) UAV swarm formation without requiring any re-training or fine-tuning of the agents. The obtained simulation results have proven the effectiveness and generalizability of our proposed MARL framework for cooperative UAV navigation.

Bayesian navigation in shallow water using passive acoustics

Autonomous underwater vehicle (AUV) navigation relying on active acoustic sources causes noise pollution, while dead reckoning leads to a localization error that increases with time. Therefore, AUV navigation based on passive acoustics is appealing. However, for AUV navigation, extracting location information with passive acoustics is a challenging signal processing task. Due to the small form factor of an AUV as a sensing platform, only a single hydrophone or a small aperture hydrophone array can be used as an acoustic sensor. Furthermore, the acoustic signals originate from uncooperative sources. Here, we propose a Bayesian navigation approach for an AUV that exploits acoustic signals generated from sources of opportunity (SOOs) in a shallow water environment. The waveguide invariant (WI) parameter is estimated from cross-correlation coefficients of non-linearly transformed tonal signals of an SOO. It is assumed that the location information of the SOO is transmitted by an automatic identification system. Additionally, the range rate is inferred using the spectrum of cross-correlatedacoustic fields over a time interval. The WI parameter estimate, the range rate estimate, and inertial measurements are fused in a Bayesian parameter estimation approach. The navigation capability is demonstrated using simulated and real data from the SwellEx-96 experiment.

A UAV Navigation Approach Based on Deep Reinforcement Learning in Large Cluttered 3D Environments

This paper is concerned with the problem of using deep reinforcement learning methods to enable safe navigation of UAVs in unknown large-scale environments containing a large number of obstacles. The ability of UAV to navigate autonomously is a precondition for performing disaster rescue and logistics deliveries. In this paper, the perception-constrained navigation of UAV is modeled as a partially observable Markov decision process (POMDP), and a fast recurrent stochastic valued gradient algorithm based on the actot-critic framework is designed for online solution. Compared with traditional SLAM-based and reactive obstacle avoidance-based approaches, the proposed navigation method can map the raw sensing information into navigation signals, and the learned policy deployed to the UAV can avoid the memory occupation and computational consumption required for real-time map building. Through experiments in a newly designed simulation environment, it is demonstrated that the proposed algorithm can enable the UAV to navigate safely in unknown cluttered large-scale environments and outperform the state-of-the-art DRL algorithm in terms of performance.

GoMap: Combining step counting technique with augmented reality for a mobile-based indoor map locator

<span lang="EN-US">In recent years, indoor navigation and localization has become a popular alternative to paper-based maps. However, the most popular navigation approach of using the global positioning satellite (GPS) does not work well indoors and the majority of current approaches designed for indoor navigation does not provide realistic solutions to key challenges, including implementation cost, accuracy, longer computation processes, and practicality. The step count method was proposed to solve these issues. This paper introduces GoMap - a mobile-based indoor locator map application, which combines the step counting technique and augmented reality (AR). The design and architecture of GoMap is described in this paper. Two small-scale studies were conducted to demonstrate the performance of GoMap. The first study found that GoMap’s performance and accuracy was comparable to other step counting app such as “Google Fit”. The second part of the study demonstrated the feasibility of the application when used in a real-world setting. The findings from the studies show that GoMap is a promising application that can help the indoor navigation process.</span>

Minimally Invasive Navigation-Guided Quad Zygomatic Implant Placement: A Comparative In Vitro Study.

Purpose: Zygomatic implants (ZIs) have been considered a reliable alternative treatment for patients with maxillary atrophy and/or maxillary defects. The use of a navigation system for assisting ZI placement could be a reliable approach for enhancing accuracy and safety. The purpose of this in vitro study was to evaluate the accuracy of a new dynamic surgical navigation system with its minimally invasive registration guide for quad zygomatic implant placement in comparison with a gold standard navigation approach. Materials and Methods: A total of 40 zygomatic implants were placed in 10 3D-printed models based on the CBCT scans of edentulous patients. For registration, a surgical registration guide with a quick response plate was used for the test group, and five hemispheric cavities as registered miniscrews in the intraoral area were used for the control group. In each model, a split-mouth approach was employed (two ZIs in bilateral zygomata) to test both systems. After ZI placement, a CBCT scan was performed and merged with pre-interventional planning. The deviations between planned and placed implants were calculated as offset basis, offset apical, and angular deviation and compared between the systems. Results: The offset basis, offset apical, and angular deviation were 1.43 ± 0.55 mm, 1.81 ± 0.68 mm, and 2.32 ± 1.59 degrees in the test group, respectively. For the control group, values of 1.48 ± 0.57 mm, 1.76 ± 0.62 mm, and 2.57 ± 1.51 degrees were measured without significant differences between groups (all P < .05). The accuracy of ZI positions (anterior and posterior) were measured without significant differences between groups. Conclusion: Two navigation systems with different registration techniques seem to achieve comparable acceptable accuracy for dynamic navigation of zygomatic implant placement. With the test group system, additional pre-interventional radiologic imaging and invasive fiducial marker insertion could be avoided.

Two-level Approach for Heterogeneous Multi-Robot Optimal Navigation

This paper proposes a two-level optimization approach for a multi-robot navigation problem. Our aim is to achieve tasks with optimal strategies, optimal trajectory planning and to give better and feasible solutions. Optimal alternatives are selected by combining game theory strategic decision with an optimal trajectory planning method. This is solved at the top level by applying Sequential Quadratic Programming (SQP). At the bottom, Pure Nash equilibrium is solved using the Simulated Annealing (SA) algorithm. The trajectory planning for the multi-robot system is performed by decomposition where the b-spline technique is initially used to describe the robots path in an environment with obstacles. The cubic spline technique is then introduced to set up the motion along the desired path. The kinematic and dynamic constraints inherent to the robot behavior are taken into account and collision constraints are handled by penalization. The proposed approach is applied to heterogeneous Unicycle Wheeled Mobile Robots and simulated in endowed obstacles environment. Optimal collision-free trajectories of the robot team are obtained with smooth line paths and good-quality solutions. Simulation results are given to show the effectiveness and robustness of proposed algorithm.

Performance of novice versus experienced surgeons for dental implant placement with freehand, static guided and dynamic navigation approaches

Lack of evidence exists related to the investigation of the accuracy and efficacy of novice versus experienced practitioners for dental implant placement. Hence, the following in vitro study was conducted to assess the accuracy of implant positioning and self-efficacy of novice compared to experienced surgeons for placing implant using freehand (FH), pilot drill-based partial guidance (PPG) and dynamic navigation (DN) approaches. The findings revealed that DN significantly improved the angular accuracy of implant placement compared with FH (P < 0.001) and PPG approaches (P < 0.001). The time required with DN was significantly longer than FH and PPG (P < 0.001), however, it was similar for both novice and experienced practitioners. The surgeon’s self-confidence questionnaire suggested that novice practitioners scored higher with both guided approaches, whereas experienced practitioners achieved higher scoring with PPG and FH compared to DN. In conclusion, implant placement executed under the guidance of DN showed high accuracy irrespective of the practitioner’s experience. The application of DN could be regarded as a beneficial tool for novices who offered high confidence of using the navigation system with the same level of accuracy and surgical time as that of experienced practitioners.

An operational concept flying GLS approaches using satellite-based augmentation systems

A new converter technology allows suitably equipped aircraft to use data provided by the satellite-based augmentation system in receivers originally designed for the ground-based augmentation landing system. For these aircraft, that system enables a lower decision altitude and, hence, improved access to airports. To make this technology usable, air crews require an operational concept and the flight crew has to be presented with the appropriate information in the form of approach charts. Two different possibilities for an operational concept were developed and the corresponding approach charts created. One option is a modified area navigation approach chart, to which the specific information is added. The other chart is an entirely separate procedure for the approach. These two options were tested with airline pilots in an Airbus A320 full-flight training simulator. During the simulator flights, aircraft performance data was recorded and the participants filled in questionnaires regarding workload and quality of the operational concept. The results show different behavior during the intercept of the final course, but all approaches remained within the required limits. The questionnaires revealed that the workload is higher during the area navigation variant and that all participants prefer the separate ground-based augmentation landing system variant.

Free Choice Navigation in the Real World: Giving Back Freedom to Wayfinders

In recent years, there has been collected evidence suggesting that increased usage of navigation assistance systems has a harmful effect on spatial cognition, including spatial knowledge acquisition. Previously, we proposed a potential remedy called Free Choice Navigation (simulation study). This novel navigation approach aims to provide the user with more freedom while navigating, and simultaneously give fewer navigation instructions. This approach also aims at increasing engagement with the environment and fostering spatial knowledge acquisition. We conducted a human-subject study with 48 participants comparing Free Choice Navigation with the widespread Turn-by-Turn approach on the outskirts of Vienna, Austria. The study showed the viability of our navigation system in real urban environments, providing fewer navigation instructions compared to the Turn-by-Turn approach (relative to the number of traversed junctions). Fewer instructions and forced engagement with the environment, however, did not result in differences concerning spatial knowledge acquisition, but interestingly, Free Choice Navigation users (without a map) could extract spatial configuration information similarly well as Turn-by-Turn users having a map. Moreover, we provide evidence that people are interested in learning more about their environments and are willing to walk longer routes to achieve it.

Performance of LiDAR-SLAM-based PNT with initial poses based on NDT scan matching algorithm

To achieve higher automation level of vehicles defined by the Society of Automotive Engineers, safety is a key requirement affecting navigation accuracy. We apply Light Detection and Ranging (LiDAR) as a main auxiliary sensor and propose LiDAR-based Simultaneously Localization and Mapping (SLAM) approach for Positioning, Navigation, and Timing. Furthermore, point cloud registration is handled with 3D Normal Distribution Transform (NDT) method. The initial guess of the LiDAR pose for LiDAR-based SLAM comes from two sources: one is the differential Global Navigation Satellite System (GNSS) solution; the other is Inertial Navigation System (INS) and GNSS integrated solution, generated with Extended Kalman Filter and motion constraints added, including Zero Velocity Update and Non-Holonomic Constraint. The experiment compares two initial guesses for scan matching in terms navigation accuracy. To emphasize the importance of a multi-sensor scheme in contrast to the conventional navigation method using the stand-alone system, the tests are conducted in both open sky area and GNSS signal block area, the latter might cause Multipath and Non-Line-Of-Sight effects. To enhance the navigation accuracy, the Fault Detection and Exclusion (FDE) mechanism is applied to correct the navigation outcome. The results show that the application of NDT and FDE for INS/GNSS integrated system can not only reach where-in-lane level navigation accuracy (0.5 m), but also enable constructing the dynamic map.